Data Extractaction and Exploration

library(opendatascot)
library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ─────────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
✓ ggplot2 3.3.3     ✓ purrr   0.3.4
✓ tibble  3.0.6     ✓ dplyr   1.0.2
✓ tidyr   1.1.2     ✓ stringr 1.4.0
✓ readr   1.4.0     ✓ forcats 0.5.0
── Conflicts ────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks stats::filter()
x dplyr::lag()    masks stats::lag()

ods_all_datasets() %>% 
  janitor::clean_names() %>% 
  filter(name == "Life Expectancy") %>% 
  select(uri)

male_hle_data <- read_csv("data/raw_data/male-healthy-life-expectancy.csv",skip = 10)

── Column specification ────────────────────────────────────────────────────────────────────────────────────────────
cols(
  `http://purl.org/linked-data/sdmx/2009/dimension#refArea` = col_character(),
  `Reference Area` = col_character(),
  `2015-2017` = col_double(),
  `2016-2018` = col_double(),
  `2017-2019` = col_double()
)

female_hle_data <- read_csv("data/raw_data/female-healthy-life-expectancy.csv", skip = 10)

── Column specification ────────────────────────────────────────────────────────────────────────────────────────────
cols(
  `http://purl.org/linked-data/sdmx/2009/dimension#refArea` = col_character(),
  `Reference Area` = col_character(),
  `2015-2017` = col_double(),
  `2016-2018` = col_double(),
  `2017-2019` = col_double()
)

hb_shapes <- readOGR(
  dsn ="data/simplified_shapefiles/health_boards/NHS_HealthBoards_2019/",
  layer = "NHS_HealthBoards_2019",
  GDAL1_integer64_policy = TRUE)

Discarded datum OSGB_1936 in CRS definition: +proj=tmerc +lat_0=49 +lon_0=-2 +k=0.9996012717 +x_0=400000 +y_0=-100000 +ellps=airy +units=m +no_defs

OGR data source with driver: ESRI Shapefile 
Source: "/Users/user/scot_stats_dashboard/data/simplified_shapefiles/health_boards/NHS_HealthBoards_2019", layer: "NHS_HealthBoards_2019"
with 14 features
It has 4 fields

library(rgeos)

rgeos version: 0.5-5, (SVN revision 640)
 GEOS runtime version: 3.8.1-CAPI-1.13.3 
 Linking to sp version: 1.4-2 
 Polygon checking: TRUE 

hb_simple <- gSimplify(hb_shapes, tol = 0.025, topologyPreserve = TRUE)

56.3950° N, 3.4308° W

uk_shape <- readOGR(
   dsn ="../Downloads/scot_stats_dashboard/bdline_essh_gb/Data/GB/",
   layer = "county_region",
   GDAL1_integer64_policy = TRUE)

Discarded datum OSGB_1936 in CRS definition: +proj=tmerc +lat_0=49 +lon_0=-2 +k=0.9996012717 +x_0=400000 +y_0=-100000 +ellps=airy +units=m +no_defs

OGR data source with driver: ESRI Shapefile 
Source: "/Users/user/Downloads/scot_stats_dashboard/bdline_essh_gb/Data/GB", layer: "county_region"
with 26 features
It has 15 fields
Integer64 fields read as doubles:  NUMBER NUMBER0 POLYGON_ID UNIT_ID 

 
 uk_simple <- gSimplify(uk_shape, tol = 0.025, topologyPreserve = TRUE)

plot(uk_simple)

library(maps)

Attaching package: ‘maps’

The following object is masked from ‘package:purrr’:

    map

UK <- map_data("world") %>% filter(region == "UK")

UK

library(broom)

hle_map_data <- spdf_fortified %>% 
  left_join(hb_lookup, by = c("id" = "id")) %>% 
  left_join(hle_data, by = c("hb_name" = "reference_area"))

library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

hle_data <- read_csv("data/clean_data/healthy_life_expectancy.csv")

── Column specification ────────────────────────────────────────────────────────────────────────────────────────────
cols(
  area_code = col_character(),
  reference_area = col_character(),
  reference_period = col_character(),
  sex = col_character(),
  measurement = col_double()
)

ref_period_var <- "2015-2017"
sex_var <- "male"


user_selections <- list(
  reference_period = "2015-2017",
  sex = "male"
)

user_selections

$ref_period
[1] "2015-2017"

$sex
[1] "male"

filtered_hle_data <- filter_df(hle_data, user_selections)

my_map

hb_shapes@data <- hb_shapes@data %>% 
  janitor::clean_names() %>% 
  left_join(hle_2015_m, by = c("hb_name" = "reference_area"))

labels <- sprintf("<strong>%s</strong><br/>%g years",
                  hb_shapes$hb_name, hb_shapes$healthy_life_expectancy) %>%
  lapply(htmltools::HTML)

# add Health Board polygons, colour based on LE, highlight on hover

my_map %>% 
    addPolygons(data = hb_shapes, color = "white",
                fillColor = ~colorQuantile(
                  "YlOrRd", (-hb_shapes$healthy_life_expectancy))
                (-hb_shapes$healthy_life_expectancy),
                weight = 1, fillOpacity = 0.9, label = labels,
                highlightOptions = highlightOptions(
                  color = "black", weight = 2,
                  opacity = 0.9, bringToFront = TRUE))